© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಿದ್ದೇವೆ
    0.41
    อ่อน
    0.39
    走り
    0.39
    дового
    0.37
     সময়ই
    0.36
    揍
    0.36
    েষ
    0.35
    ğe
    0.35
    tedir
    0.35
     exhaustion
    0.35
    POSITIVE LOGITS
     derived
    0.37
    黙
    0.37
    derived
    0.36
     ٹی
    0.36
    倬
    0.36
     వచ్చ
    0.36
     cuyo
    0.35
    derive
    0.34
    σί
    0.34
     derives
    0.33
    Activations Density 0.000%

    No Known Activations